Wallas Henrique 8baf85e4e9 [Doc] Compatibility matrix for mutual exclusive features (#8512) ...

Signed-off-by: Wallas Santos <wallashss@ibm.com>

2024-10-11 11:18:50 -07:00

..

__init__.py

[Core] Refactor Attention Take 2 (#3462)

2024-03-25 04:39:33 +00:00

abstract.py

[Encoder decoder] Add cuda graph support during decoding for encoder-decoder models (#7631)

2024-09-17 07:35:01 -07:00

blocksparse_attn.py

[Spec Decode] (1/2) Remove batch expansion (#8839)

2024-10-01 16:04:42 -07:00

flash_attn.py

[misc] add forward context for attention (#9029)

2024-10-03 12:09:42 -07:00

flashinfer.py

[core] use forward context for flash infer (#9097)

2024-10-05 19:37:31 -07:00

ipex_attn.py

[torch.compile] use empty tensor instead of None for profiling (#8875)

2024-09-27 08:11:32 -07:00

openvino.py

[OpenVINO] Enable GPU support for OpenVINO vLLM backend (#8192)

2024-10-02 17:50:01 -04:00

pallas.py

[torch.compile] use empty tensor instead of None for profiling (#8875)

2024-09-27 08:11:32 -07:00

placeholder_attn.py

[Model] Support Mamba (#6484)

2024-10-11 15:40:06 +00:00

rocm_flash_attn.py

[Doc] Compatibility matrix for mutual exclusive features (#8512)

2024-10-11 11:18:50 -07:00

torch_sdpa.py

[Hardware][CPU] Cross-attention and Encoder-Decoder models support on CPU backend (#9089)

2024-10-07 06:50:35 +00:00

utils.py

[Spec Decode] (1/2) Remove batch expansion (#8839)

2024-10-01 16:04:42 -07:00

xformers.py

[Spec Decode] (1/2) Remove batch expansion (#8839)

2024-10-01 16:04:42 -07:00